# Tabsec

> Tabsec is endpoint-native AI Detection and Response (AIDR) for organizations that need to discover, inventory, and assess the risk of AI agents — and the surfaces that steer them — running across enterprise hosts.

Tabsec helps security engineering, security leadership, GRC, risk, compliance, platform engineering, and AI engineering teams govern agent runtime activity. It focuses on host evidence rather than self-reported agent metadata.

Core surfaces Tabsec is designed to discover and inventory:
- AI coding agents and coding harnesses
- Agent configuration and memory artifacts (CLAUDE.md, AGENTS.md, and similar)
- MCP client configurations and the MCP server entries they declare
- Agent capability extensions: skills, hooks, and plugins
- SDK-based agents and agent libraries
- Local model runners and agentic automation

Core evidence Tabsec is designed to provide:
- Process lineage
- User identity
- Libraries and configuration
- Credentials and host telemetry
- Evidence-backed risk findings over agent-surface content (semantic and measurement signals, mapped to MITRE ATLAS) — readable by your own agents over MCP
- Policy-shaped findings for webhook routing and SIEM/SOAR export

## Primary

- [Tabsec website](https://tabsec.io/): Product overview, at-a-glance product facts, platform workflow, compliance posture, and access request form.
- [Full AI-readable Tabsec brief](https://tabsec.io/llms-full.txt): Plain-text summary of Tabsec positioning, detected surfaces, evidence model, deployment model, buyer fit, and contact path.
- [Sitemap](https://tabsec.io/sitemap.xml): Crawlable URLs for the public Tabsec site.

## Contact

- [Email Tabsec](mailto:hello@tabsec.io): Contact for design partner and access requests.